Optimization of an MRT train schedule: reducing maximum traction power by using genetic algorithms

Because of the traction power load characteristics of mass rapid transit (MRT) systems, a significant difference exists between the peak and valley of the traction power load curve. Furthermore, an extremely high traction power peak occurs if numerous trains are accelerating simultaneously. Careful train scheduling can avoid the simultaneous acceleration of too many trains, thus reducing maximum traction power. This paper employs genetic algorithms to optimize train scheduling and uses the Kaohsiung MRT system as an example. Simulation results show that the proposed method can significantly reduce the maximum traction power.

[1]  Lalit M. Patnaik,et al.  Genetic algorithms: a survey , 1994, Computer.

[2]  Anastasios G. Bakirtzis,et al.  A genetic algorithm solution to the unit commitment problem , 1996 .

[3]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[4]  Kit Po Wong,et al.  Combined genetic algorithm/simulated annealing/fuzzy set approach to short-term generation scheduling with take-or-pay fuel contract , 1996 .

[5]  Fushuan Wen,et al.  Bicriterion optimisation for traction substations in mass rapid transit systems using genetic algorithm , 1998 .

[6]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[7]  G. Sheblé,et al.  Genetic algorithm solution of economic dispatch with valve point loading , 1993 .

[8]  T. Suzuki.  DC power-supply system with inverting substations for traction systems using regenerative brakes , 1982 .

[9]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[10]  W Spatny.  SUBSTATIONS FOR THE POWER SUPPLY TO THE SAO PAULO METRO , 1978 .

[11]  Chung-Fu Chang,et al.  Optimising train movements through coast control using genetic algorithms , 1997 .

[12]  A.M.M. Khan,et al.  Computer simulation of transit power systems , 1998 .

[13]  Sam Kwong,et al.  Genetic algorithms: concepts and applications [in engineering design] , 1996, IEEE Trans. Ind. Electron..

[14]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[15]  B. Liljeqvist.  The use Of Voltage Controlled Thyristor Converters in Power Supply For DC Traction Systems , 1992, Proceedings of the ASME/IEEE Spring Joint Railroad Conference.

[16]  Chien-Hsing Lee,et al.  Effects of grounding schemes on rail potential and stray currents in Taipei Rail Transit Systems , 2001 .

[17]  Dipti Srinivasan,et al.  Application of tabu search in optimal system design and operation of MRT power supply systems , 1999 .

[18]  B. S. Thia,et al.  Economy/regularity fuzzy-logic control of DC railway systems using event-driven approach , 1996 .

[19]  Sam Kwong,et al.  Genetic algorithms: concepts and applications [in engineering design] , 1996, IEEE Trans. Ind. Electron..

[20]  Hong-Tzer Yang,et al.  A parallel genetic algorithm approach to solving the unit commitment problem: implementation on the transputer networks , 1997 .

[21]  J. B. Flowers.  Load sharing with thyristor controlled rectifier substations , 1995, Proceedings of the 1995 IEEE/ASME Joint Railroad Conference.